Singular Learning of Deep Multilayer Perceptrons for EEG-Based Emotion Recognition

Human emotion recognition is an important issue in human–computer interactions, and electroencephalograph (EEG) has been widely applied to due its high reliability. In recent years, methods based on deep learning technology have reached the state-of-the-art performance EEG-based recognition. However, there exist singularities parameter space of neural networks, which may dramatically slow down training process. It very worthy investigate specific influence when applying networks this paper, we mainly focus problem, analyze singular dynamics multilayer perceptrons theoretically numerically. The results can help us design better algorithms overcome serious for